Mengjie Zhang

Ying Bi, Bing Xue, Pablo Mesejo et al.

Computer vision (CV) is a big and important field in artificial intelligence covering a wide range of applications. Image analysis is a major task in CV aiming to extract, analyse and understand the visual content of images. However, image-related tasks are very challenging due to many factors, e.g., high variations across images, high dimensionality, domain expertise requirement, and image distortions. Evolutionary computation (EC) approaches have been widely used for image analysis with significant achievement. However, there is no comprehensive survey of existing EC approaches to image analysis. To fill this gap, this paper provides a comprehensive survey covering all essential EC approaches to important image analysis tasks including edge detection, image segmentation, image feature analysis, image classification, object detection, and others. This survey aims to provide a better understanding of evolutionary computer vision (ECV) by discussing the contributions of different approaches and exploring how and why EC is used for CV and image analysis. The applications, challenges, issues, and trends associated to this research field are also discussed and summarised to provide further guidelines and opportunities for future research.

Ying Bi, Bing Xue, Mengjie Zhang

Data-efficient image classification is a challenging task that aims to solve image classification using small training data. Neural network-based deep learning methods are effective for image classification, but they typically require large-scale training data and have major limitations such as requiring expertise to design network architectures and having poor interpretability. Evolutionary deep learning is a recent hot topic that combines evolutionary computation with deep learning. However, most evolutionary deep learning methods focus on evolving architectures of neural networks, which still suffer from limitations such as poor interpretability. To address this, this paper proposes a new genetic programming-based evolutionary deep learning approach to data-efficient image classification. The new approach can automatically evolve variable-length models using many important operators from both image and classification domains. It can learn different types of image features from colour or gray-scale images, and construct effective and diverse ensembles for image classification. A flexible multi-layer representation enables the new approach to automatically construct shallow or deep models/trees for different tasks and perform effective transformations on the input data via multiple internal nodes. The new approach is applied to solve five image classification tasks with different training set sizes. The results show that it achieves better performance in most cases than deep learning methods for data-efficient image classification. A deep analysis shows that the new approach has good convergence and evolves models with high interpretability, different lengths/sizes/shapes, and good transferability.

Christian Raymond, Qi Chen, Bing Xue et al.

In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for learning model-agnostic loss functions via a hybrid neuro-symbolic search approach. The framework first uses evolution-based methods to search the space of primitive mathematical operations to find a set of symbolic loss functions. Second, the set of learned loss functions are subsequently parameterized and optimized via an end-to-end gradient-based training procedure. The versatility of the proposed framework is empirically validated on a diverse set of supervised learning tasks. Results show that the meta-learned loss functions discovered by the newly proposed method outperform both the cross-entropy loss and state-of-the-art loss function learning methods on a diverse range of neural network architectures and datasets.

Peng Zeng, Xiaotian Song, Andrew Lensen et al.

Symbolic regression (SR) is the process of discovering hidden relationships from data with mathematical expressions, which is considered an effective way to reach interpretable machine learning (ML). Genetic programming (GP) has been the dominator in solving SR problems. However, as the scale of SR problems increases, GP often poorly demonstrates and cannot effectively address the real-world high-dimensional problems. This limitation is mainly caused by the stochastic evolutionary nature of traditional GP in constructing the trees. In this paper, we propose a differentiable approach named DGP to construct GP trees towards high-dimensional SR for the first time. Specifically, a new data structure called differentiable symbolic tree is proposed to relax the discrete structure to be continuous, thus a gradient-based optimizer can be presented for the efficient optimization. In addition, a sampling method is proposed to eliminate the discrepancy caused by the above relaxation for valid symbolic expressions. Furthermore, a diversification mechanism is introduced to promote the optimizer escaping from local optima for globally better solutions. With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks. The experiment results reveal that DGP can outperform these chosen peer competitors on high-dimensional regression benchmarks with dimensions varying from tens to thousands. In addition, on the synthetic SR problems, the proposed DGP method can also achieve the best recovery rate even with different noisy levels. It is believed this work can facilitate SR being a powerful alternative to interpretable ML for a broader range of real-world problems.

Carl McMillan, Junhong Zhao, Bing Xue et al.

The aquaculture sector in New Zealand is experiencing rapid expansion, with a particular emphasis on mussel exports. As the demands of mussel farming operations continue to evolve, the integration of artificial intelligence and computer vision techniques, such as intelligent object detection, is emerging as an effective approach to enhance operational efficiency. This study delves into advancing buoy detection by leveraging deep learning methodologies for intelligent mussel farm monitoring and management. The primary objective centers on improving accuracy and robustness in detecting buoys across a spectrum of real-world scenarios. A diverse dataset sourced from mussel farms is captured and labeled for training, encompassing imagery taken from cameras mounted on both floating platforms and traversing vessels, capturing various lighting and weather conditions. To establish an effective deep learning model for buoy detection with a limited number of labeled data, we employ transfer learning techniques. This involves adapting a pre-trained object detection model to create a specialized deep learning buoy detection model. We explore different pre-trained models, including YOLO and its variants, alongside data diversity to investigate their effects on model performance. Our investigation demonstrates a significant enhancement in buoy detection performance through deep learning, accompanied by improved generalization across diverse weather conditions, highlighting the practical effectiveness of our approach.

Christian Raymond, Qi Chen, Bing Xue et al.

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often improving a model's training dynamics and final inference performance. However, a significant limitation of these techniques is that the loss functions are meta-learned in an offline fashion, where the meta-objective only considers the very first few steps of training, which is a significantly shorter time horizon than the one typically used for training deep neural networks. This causes significant bias towards loss functions that perform well at the very start of training but perform poorly at the end of training. To address this issue we propose a new loss function learning technique for adaptively updating the loss function online after each update to the base model parameters. The experimental results show that our proposed method consistently outperforms the cross-entropy loss and offline loss function learning techniques on a diverse range of neural network architectures and datasets.

Ya Shen, Gang Chen, Hui Ma et al.

Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources. However, existing deep reinforcement learning (DRL) schedulers remain limited by rigid, single-path inference architectures that struggle to handle diverse scheduling scenarios. We introduce \textbf{DEFT} (\textbf{D}eadline-p\textbf{E}rceptive Mixture-o\textbf{F}-Exper\textbf{t}s), an innovative DRL policy architecture that leverages a specialized mixture of experts, each trained to manage different levels of deadline tightness. To our knowledge, DEFT is the first to introduce and validate a Mixture-of-Experts architecture for dynamic cloud workflow scheduling. By adaptively routing decisions through the most appropriate experts, DEFT is capable of meeting a broad spectrum of deadline requirements that no single expert can achieve. Central to DEFT is a \textbf{graph-adaptive} gating mechanism that encodes workflow deadlines and DAGs, task states, and VM conditions, using cross-attention to guide expert activation in a fine-grained, deadline-sensitive manner. Experiments on dynamic cloud workflow benchmarks demonstrate that DEFT significantly reduces execution cost and deadline violations, outperforming multiple state-of-the-art DRL baselines.

Xiangling Chen, Yi Mei, Mengjie Zhang

Recent advances in neural neighborhood search methods have shown potential in tackling Vehicle Routing Problems (VRPs). However, most existing approaches rely on simplistic state representations and fuse heterogeneous information via naive concatenation, limiting their ability to capture rich structural and semantic context. To address these limitations, we propose GAMA, a neural neighborhood search method with Graph-aware Multi-modal Attention model in VRP. GAMA encodes the problem instance and its evolving solution as distinct modalities using graph neural networks, and models their intra- and inter-modal interactions through stacked self- and cross-attention layers. A gated fusion mechanism further integrates the multi-modal representations into a structured state, enabling the policy to make informed and generalizable operator selection decisions. Extensive experiments conducted across various synthetic and benchmark instances demonstrate that the proposed algorithm GAMA significantly outperforms the recent neural baselines. Further ablation studies confirm that both the multi-modal attention mechanism and the gated fusion design play a key role in achieving the observed performance gains.

Ya Shen, Gang Chen, Hui Ma et al.

Cost-aware Dynamic Workflow Scheduling (CADWS) is a key challenge in cloud computing, focusing on devising an effective scheduling policy to efficiently schedule dynamically arriving workflow tasks, represented as Directed Acyclic Graphs (DAG), to suitable virtual machines (VMs). Deep reinforcement learning (DRL) has been widely employed for automated scheduling policy design. However, the performance of DRL is heavily influenced by the design of the problem-tailored policy network and is highly sensitive to hyperparameters and the design of reward feedback. Considering the above-mentioned issues, this study proposes a novel DRL method combining Graph Attention Networks-based policy network and Evolution Strategy, referred to as GATES. The contributions of GATES are summarized as follows: (1) GATES can capture the impact of current task scheduling on subsequent tasks by learning the topological relationships between tasks in a DAG. (2) GATES can assess the importance of each VM to the ready task, enabling it to adapt to dynamically changing VM resources. (3) Utilizing Evolution Strategy's robustness, exploratory nature, and tolerance for delayed rewards, GATES achieves stable policy learning in CADWS. Extensive experimental results demonstrate the superiority of the proposed GATES in CADWS, outperforming several state-of-the-art algorithms. The source code is available at: https://github.com/YaShen998/GATES.

Hengzhe Zhang, Qi Chen, Bing Xue et al.

In recent years, genetic programming (GP)-based evolutionary feature construction has achieved significant success. However, a primary challenge with evolutionary feature construction is its tendency to overfit the training data, resulting in poor generalization on unseen data. In this research, we draw inspiration from PAC-Bayesian theory and propose using sharpness-aware minimization in function space to discover symbolic features that exhibit robust performance within a smooth loss landscape in the semantic space. By optimizing sharpness in conjunction with cross-validation loss, as well as designing a sharpness reduction layer, the proposed method effectively mitigates the overfitting problem of GP, especially when dealing with a limited number of instances or in the presence of label noise. Experimental results on 58 real-world regression datasets show that our approach outperforms standard GP as well as six state-of-the-art complexity measurement methods for GP in controlling overfitting. Furthermore, the ensemble version of GP with sharpness-aware minimization demonstrates superior performance compared to nine fine-tuned machine learning and symbolic regression algorithms, including XGBoost and LightGBM.

Christian Raymond, Qi Chen, Bing Xue et al.

In this paper, we develop upon the topic of loss function learning, an emergent meta-learning paradigm that aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for task and model-agnostic loss function learning via a hybrid search approach. The framework first uses genetic programming to find a set of symbolic loss functions. Second, the set of learned loss functions is subsequently parameterized and optimized via unrolled differentiation. The versatility and performance of the proposed framework are empirically validated on a diverse set of supervised learning tasks. Results show that the learned loss functions bring improved convergence, sample efficiency, and inference performance on tabulated, computer vision, and natural language processing problems, using a variety of task-specific neural network architectures.

Xiao-Cheng Liao, Yi Mei, Mengjie Zhang

Recently, learning-based approaches, have achieved significant success in automatically devising effective traffic signal control strategies. In particular, as a powerful evolutionary machine learning approach, Genetic Programming (GP) is utilized to evolve human-understandable phase urgency functions to measure the urgency of activating a green light for a specific phase. However, current GP-based methods are unable to treat the common traffic features of different traffic signal phases consistently. To address this issue, we propose to use a symmetric phase urgency function to calculate the phase urgency for a specific phase based on the current road conditions. This is represented as an aggregation of two shared subtrees, each representing the urgency of a turn movement in the phase. We then propose a GP method to evolve the symmetric phase urgency function. We evaluate our proposed method on the well-known cityflow traffic simulator, based on multiple public real-world datasets. The experimental results show that the proposed symmetric urgency function representation can significantly improve the performance of the learned traffic signal control policies over the traditional GP representation on a wide range of scenarios. Further analysis shows that the proposed method can evolve effective, human-understandable and easily deployable traffic signal control policies.

Haoran Gu, Handing Wang, Yi Mei et al.

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context algorithm have shown strong performance and efficiency. However, inappropriate preference representations and training with imbalanced reward scores limit the performance of such algorithms. In this work, we introduce ParetoHqD that addresses the above issues by representing human preferences as preference directions in the objective space and regarding data near the Pareto front as ''high-quality'' data. For each preference, ParetoHqD follows a two-stage supervised fine-tuning process, where each stage uses an individual Pareto high-quality training set that best matches its preference direction. The experimental results have demonstrated the superiority of ParetoHqD over five baselines on two multiobjective alignment tasks.

Su Nguyen, Dhananjay Thiruvady, Yuan Sun et al.

Resource constrained job scheduling is a hard combinatorial optimisation problem that originates in the mining industry. Off-the-shelf solvers cannot solve this problem satisfactorily in reasonable timeframes, while other solution methods such as many evolutionary computation methods and matheuristics cannot guarantee optimality and require low-level customisation and specialised heuristics to be effective. This paper addresses this gap by proposing a genetic programming algorithm to discover efficient search strategies of constraint programming for resource-constrained job scheduling. In the proposed algorithm, evolved programs represent variable selectors to be used in the search process of constraint programming, and their fitness is determined by the quality of solutions obtained for training instances. The novelties of this algorithm are (1) a new representation of variable selectors, (2) a new fitness evaluation scheme, and (3) a pre-selection mechanism. Tests with a large set of random and benchmark instances, the evolved variable selectors can significantly improve the efficiency of constraining programming. Compared to highly customised metaheuristics and hybrid algorithms, evolved variable selectors can help constraint programming identify quality solutions faster and proving optimality is possible if sufficiently large run-times are allowed. The evolved variable selectors are especially helpful when solving instances with large numbers of machines.

Hengzhe Zhang, Qi Chen, Bing Xue et al.

Large language models (LLMs) have revolutionized algorithm development, yet their application in symbolic regression, where algorithms automatically discover symbolic expressions from data, remains constrained and is typically designed manually by human experts. In this paper, we propose a meta learning framework that enables LLMs to automatically design selection operators for evolutionary symbolic regression algorithms. We first identify two key limitations in existing LLM-based algorithm evolution techniques: a lack of semantic guidance and code bloat. The absence of semantic awareness can lead to ineffective exchange of useful code components, and bloat results in unnecessarily complex components, both of which can reduce the interpretability of the designed algorithm or hinder evolutionary learning progress. To address these issues, we enhance the LLM-based evolution framework for meta symbolic regression with two key innovations: a complementary, semantics-aware selection operator and bloat control. Additionally, we embed domain knowledge into the prompt, enabling the LLM to generate more effective and contextually relevant selection operators. Our experimental results on symbolic regression benchmarks show that LLMs can devise selection operators that outperform nine expert-designed baselines, achieving state-of-the-art performance. Moreover, the evolved operator can further improve the state-of-the-art symbolic regression algorithm, achieving the best performance among 26 symbolic regression and machine learning algorithms across 116 regression datasets. This demonstrates that LLMs can exceed expert-level algorithm design for symbolic regression.

Saining Liu, Yi Mei, Mengjie Zhang

Manually designing (meta-)heuristics for the Vehicle Routing Problem (VRP) is a challenging task that requires significant domain expertise. Recently, data-driven approaches have emerged as a promising solution, automatically learning heuristics that perform well on training instances and generalize to unseen test cases. Such an approach learns (meta-)heuristics that can perform well on the training instances, expecting it to generalize well on the unseen test instances. A recent method, named GPGLS, uses Genetic Programming (GP) to learn the utility function in Guided Local Search (GLS) and solved large scale VRP effectively. However, the selection of appropriate training instances during the learning process remains an open question, with most existing studies including GPGLS relying on random instance selection. To address this, we propose a novel method, CL-GPGLS, which integrates Curriculum Learning (CL) into GPGLS. Our approach leverages a predefined curriculum to introduce training instances progressively, starting with simpler tasks and gradually increasing complexity, enabling the model to better adapt and optimize for large-scale VRP (LSVRP). Extensive experiments verify the effectiveness of CL-GPGLS, demonstrating significant performance improvements over three baseline methods.

Quan Long, Bin Wang, Bing Xue et al.

To address the issue of interpretability in multilayer perceptrons (MLPs), Kolmogorov-Arnold Networks (KANs) are introduced in 2024. However, optimizing KAN structures is labor-intensive, typically requiring manual intervention and parameter tuning. This paper proposes GA-KAN, a genetic algorithm-based approach that automates the optimization of KANs, requiring no human intervention in the design process. To the best of our knowledge, this is the first time that evolutionary computation is explored to optimize KANs automatically. Furthermore, inspired by the use of sparse connectivity in MLPs in effectively reducing the number of parameters, GA-KAN further explores sparse connectivity to tackle the challenge of extensive parameter spaces in KANs. GA-KAN is validated on two toy datasets, achieving optimal results without the manual tuning required by the original KAN. Additionally, GA-KAN demonstrates superior performance across five classification datasets, outperforming traditional methods on all datasets and providing interpretable symbolic formulae for the Wine and Iris datasets, thereby enhancing model transparency. Furthermore, GA-KAN significantly reduces the number of parameters over the standard KAN across all the five datasets. The core contributions of GA-KAN include automated optimization, a new encoding strategy, and a new decoding process, which together improve the accuracy and interpretability, and reduce the number of parameters.

Yuqiao Liu, Yanan Sun, Bing Xue et al.

Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labour intensive because of the trial-and-error process, and also not easy to realize due to the rare expertise in practice. Neural Architecture Search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, Evolutionary Computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This paper reviews over 200 papers of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles as well as justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.

Yanan Sun, Ziyao Ren, Gary G. Yen et al.

The superiority of Convolutional Neural Networks (CNNs) largely relies on their architectures that are often manually crafted with extensive human expertise. Unfortunately, such kind of domain knowledge is not necessarily owned by each of the users interested. Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs. There have been various state-of-the-art data mining algorithms at hand, while there is only rare work that has been done for the mining. One of the main reasons is the gap between CNN architectures and data mining algorithms. Specifically, the current CNN architecture descriptions cannot be exactly vectorized to the input of data mining algorithms. In this paper, we propose a unified approach, named ArcText, to describing CNN architectures based on text. Particularly, four different units and an ordering method have been elaborately designed in ArcText, to uniquely describe the same architecture with sufficient information. Also, the resulted description can be exactly converted back to the corresponding CNN architecture. ArcText bridges the gap between CNN architectures and data mining researchers, and has the potentiality to be utilized to wider scenarios.

Andrew Lensen, Bing Xue, Mengjie Zhang

Data visualisation is a key tool in data mining for understanding big datasets. Many visualisation methods have been proposed, including the well-regarded state-of-the-art method t-Distributed Stochastic Neighbour Embedding. However, the most powerful visualisation methods have a significant limitation: the manner in which they create their visualisation from the original features of the dataset is completely opaque. Many domains require an understanding of the data in terms of the original features; there is hence a need for powerful visualisation methods which use understandable models. In this work, we propose a genetic programming approach named GPtSNE for evolving interpretable mappings from a dataset to highquality visualisations. A multi-objective approach is designed that produces a variety of visualisations in a single run which give different trade-offs between visual quality and model complexity. Testing against baseline methods on a variety of datasets shows the clear potential of GP-tSNE to allow deeper insight into data than that provided by existing visualisation methods. We further highlight the benefits of a multi-objective approach through an in-depth analysis of a candidate front, which shows how multiple models can

Andrew Lensen, Bing Xue, Mengjie Zhang

Clustering is a difficult and widely-studied data mining task, with many varieties of clustering algorithms proposed in the literature. Nearly all algorithms use a similarity measure such as a distance metric (e.g. Euclidean distance) to decide which instances to assign to the same cluster. These similarity measures are generally pre-defined and cannot be easily tailored to the properties of a particular dataset, which leads to limitations in the quality and the interpretability of the clusters produced. In this paper, we propose a new approach to automatically evolving similarity functions for a given clustering algorithm by using genetic programming. We introduce a new genetic programming-based method which automatically selects a small subset of features (feature selection) and then combines them using a variety of functions (feature construction) to produce dynamic and flexible similarity functions that are specifically designed for a given dataset. We demonstrate how the evolved similarity functions can be used to perform clustering using a graph-based representation. The results of a variety of experiments across a range of large, high-dimensional datasets show that the proposed approach can achieve higher and more consistent performance than the benchmark methods. We further extend the proposed approach to automatically produce multiple complementary similarity functions by using a multi-tree approach, which gives further performance improvements. We also analyse the interpretability and structure of the automatically evolved similarity functions to provide insight into how and why they are superior to standard distance metrics.

Benjamin Patrick Evans, Harith Al-Sahaf, Bing Xue et al.

Image classification is an essential task in computer vision, which aims to categorise a set of images into different groups based on some visual criteria. Existing methods, such as convolutional neural networks, have been successfully utilised to perform image classification. However, such methods often require human intervention to design a model. Furthermore, such models are difficult to interpret and it is challenging to analyse the patterns of different classes. This paper presents a hybrid (memetic) approach combining genetic programming (GP) and Gradient-based optimisation for image classification to overcome the limitations mentioned. The performance of the proposed method is compared to a baseline version (without local search) on four binary classification image datasets to provide an insight into the usefulness of local search mechanisms for enhancing the performance of GP.

Andrew Lensen, Bing Xue, Mengjie Zhang

Exploratory data analysis is a fundamental aspect of knowledge discovery that aims to find the main characteristics of a dataset. Dimensionality reduction, such as manifold learning, is often used to reduce the number of features in a dataset to a manageable level for human interpretation. Despite this, most manifold learning techniques do not explain anything about the original features nor the true characteristics of a dataset. In this paper, we propose a genetic programming approach to manifold learning called GP-MaL which evolves functional mappings from a high-dimensional space to a lower dimensional space through the use of interpretable trees. We show that GP-MaL is competitive with existing manifold learning algorithms, while producing models that can be interpreted and re-used on unseen data. A number of promising future directions of research are found in the process.

Gang Chen, Yiming Peng, Mengjie Zhang

Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performance, we will develop a new DRL algorithm in this paper that seamless integrates entropy-induced and bootstrap-induced techniques for efficient and deep exploration of the learning environment. Specifically, a general form of Tsallis entropy regularizer will be utilized to drive entropy-induced exploration based on efficient approximation of optimal action-selection policies. Different from many existing works that rely on action dithering strategies for exploration, our algorithm is efficient in exploring actions with clear exploration value. Meanwhile, by employing an ensemble of Q-networks under varied Tsallis entropy regularization, the diversity of the ensemble can be further enhanced to enable effective bootstrap-induced exploration. Experiments on Atari game playing tasks clearly demonstrate that our new algorithm can achieve more efficient and effective exploration for DRL, in comparison to recently proposed exploration methods including Bootstrapped Deep Q-Network and UCB Q-Ensemble.

Yanan Sun, Bing Xue, Mengjie Zhang et al.

Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For most state-of-the-art CNNs, their architectures are often manually-designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this paper, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its "automatic" characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, by comparing to the state-of-the-art peer competitors covering eight manually-designed CNNs, seven automatic+manually tuning and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually-designed and automatic+manually tuning CNNs, while consumes much less of computational resource.

Gang Chen, Yiming Peng, Mengjie Zhang

Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves data efficiency by performing multiple epochs of \emph{clipped policy optimization} from sampled data. Although clipping in PPO stands for an important new mechanism for efficient and reliable policy update, it may fail to adaptively improve learning performance in accordance with the importance of each sampled state. To address this issue, a new surrogate learning objective featuring an adaptive clipping mechanism is proposed in this paper, enabling us to develop a new algorithm, known as PPO-$λ$. PPO-$λ$ optimizes policies repeatedly based on a theoretical target for adaptive policy improvement. Meanwhile, destructively large policy update can be effectively prevented through both clipping and adaptive control of a hyperparameter $λ$ in PPO-$λ$, ensuring high learning reliability. PPO-$λ$ enjoys the same simple and efficient design as PPO. Empirically on several Atari game playing tasks and benchmark control tasks, PPO-$λ$ also achieved clearly better performance than PPO.

Yanan Sun, Bing Xue, Mengjie Zhang et al.

Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years. However, they are unable to construct the state-of-the-art convolutional neural networks due to their intrinsic architectures. In this regard, we propose a flexible convolutional auto-encoder by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional convolutional auto-encoder. We also design an architecture discovery method by using particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed flexible convolutional auto-encoder with much less computational resource and without any manual intervention. We use the designed architecture optimization algorithm to test the proposed flexible convolutional auto-encoder through utilizing one graphic processing unit card on four extensively used image classification datasets. Experimental results show that our work in this paper significantly outperform the peer competitors including the state-of-the-art algorithm.

Yanan Sun, Bing Xue, Mengjie Zhang et al.

Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the unpredictable optimal depth in convolutional neural networks. In addition, a new representation scheme is developed for effectively initializing connection weights of deep convolutional neural networks, which is expected to avoid networks getting stuck into local minima which is typically a major issue in the backward gradient-based optimization. Furthermore, a novel fitness evaluation method is proposed to speed up the heuristic search with substantially less computational resource. The proposed algorithm is examined and compared with 22 existing algorithms on nine widely used image classification tasks, including the state-of-the-art methods. The experimental results demonstrate the remarkable superiority of the proposed algorithm over the state-of-the-art algorithms in terms of classification error rate and the number of parameters (weights).

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang et al.

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly learns a shared encoding representation for two tasks: i) supervised classification of labeled source data, and ii) unsupervised reconstruction of unlabeled target data.In this way, the learnt representation not only preserves discriminability, but also encodes useful information from the target domain. Our new DRCN model can be optimized by using backpropagation similarly as the standard neural networks. We evaluate the performance of DRCN on a series of cross-domain object recognition tasks, where DRCN provides a considerable improvement (up to ~8% in accuracy) over the prior state-of-the-art algorithms. Interestingly, we also observe that the reconstruction pipeline of DRCN transforms images from the source domain into images whose appearance resembles the target dataset. This suggests that DRCN's performance is due to constructing a single composite representation that encodes information about both the structure of target images and the classification of source images. Finally, we provide a formal analysis to justify the algorithm's objective in domain adaptation context.

Muhammad Ghifary, David Balduzzi, W. Bastiaan Kleijn et al.

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different from (but related to) the target. Two closely related frameworks, domain adaptation and domain generalization, are concerned with such tasks, where the only difference between those frameworks is the availability of the unlabeled target data: domain adaptation can leverage unlabeled target information, while domain generalization cannot. We propose Scatter Component Analyis (SCA), a fast representation learning algorithm that can be applied to both domain adaptation and domain generalization. SCA is based on a simple geometrical measure, i.e., scatter, which operates on reproducing kernel Hilbert space. SCA finds a representation that trades between maximizing the separability of classes, minimizing the mismatch between domains, and maximizing the separability of data; each of which is quantified through scatter. The optimization problem of SCA can be reduced to a generalized eigenvalue problem, which results in a fast and exact solution. Comprehensive experiments on benchmark cross-domain object recognition datasets verify that SCA performs much faster than several state-of-the-art algorithms and also provides state-of-the-art classification accuracy in both domain adaptation and domain generalization. We also show that scatter can be used to establish a theoretical generalization bound in the case of domain adaptation.

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang et al.

The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance for cross-domain object recognition. Our algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in the appearance of objects. Instead of reconstructing images from noisy versions, MTAE learns to transform the original image into analogs in multiple related domains. It thereby learns features that are robust to variations across domains. The learnt features are then used as inputs to a classifier. We evaluated the performance of the algorithm on benchmark image recognition datasets, where the task is to learn features from multiple datasets and to then predict the image label from unseen datasets. We found that (denoising) MTAE outperforms alternative autoencoder-based models as well as the current state-of-the-art algorithms for domain generalization.

Muhammad Ghifary, W. Bastiaan Kleijn, Mengjie Zhang

We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the distribution mismatch between the source and target domains in the latent space. From experiments, we demonstrate that the MMD regularization is an effective tool to provide good domain adaptation models on both SURF features and raw image pixels of a particular image data set. We also show that our proposed model, preceded by the denoising auto-encoder pretraining, achieves better performance than recent benchmark models on the same data sets. This work represents the first study of MMD measure in the context of neural networks.